Security audit
Finance Office Automation
Security checks for vulnerabilities and agentic risk
Overview
This skill is a document-template and workflow-drafting aid for financial office work, with clear limits against accessing systems, sending mail, or executing approvals.
Before installing, treat its regulatory-update section and workflow thresholds as reference material only, verify current requirements against official institutional policy, and avoid pasting customer identifiers, credentials, account numbers, or non-public business data into prompts.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep